Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to constants or fixed values in mathematical or scientific contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.98
    RegistryLite
    -0.88
     незавершена
    -0.83
    lujah
    -0.80
    τεύ
    -0.78
    moiselle
    -0.76
     wigs
    -0.75
    Fleur
    -0.72
    ewear
    -0.71
     Judi
    -0.70
    POSITIVE LOGITS
     Constant
    1.34
    Constant
    1.30
     constants
    1.28
    CONSTANT
    1.25
     constant
    1.21
     CONSTANT
    1.18
    constant
    1.16
     Constantine
    1.09
     Konst
    1.08
     Constants
    1.04
    Act Density 0.025%

    No Known Activations